Title :
Pole placement control of discrete time systems preceded with hysteresis via dynamic neural network compensator
Author :
Lu, Tianshun ; Tan, Yonghong ; Su, Chun-Yi
Author_Institution :
Dept. of Mech. Eng., Concordia Univ., Montreal, Que., Canada
Abstract :
A control strategy for discrete time systems preceded with dominant hysteresis is presented in this paper. In this strategy, a recurrent neural network with hysteron (RNNH) is applied for the construction of the nonlinear compensator to remove the effect of the hysteresis. Then the incremental pole placement control approach is used for the control of the systems with the neural compensator. Finally, numerical simulation examples are illustrated to show the performance of the proposed strategy.
Keywords :
compensation; control nonlinearities; control system synthesis; discrete time systems; hysteresis; neurocontrollers; pole assignment; recurrent neural nets; control strategy; discrete time systems; dominant hysteresis; dynamic neural network compensator; hysteresis nonlinearities; incremental pole placement control approach; nonlinear compensator; numerical simulation examples; pole placement control; recurrent neural network with hysteron; Control design; Control systems; Discrete time systems; Hysteresis; Inverse problems; Neural networks; Numerical simulation; Piezoelectric actuators; Recurrent neural networks; State feedback;
Conference_Titel :
Intelligent Control, 2002. Proceedings of the 2002 IEEE International Symposium on
Print_ISBN :
0-7803-7620-X
DOI :
10.1109/ISIC.2002.1157767
